Robust Finite-State Controllers for Uncertain POMDPs
Authors: Murat Cubuktepe, Nils Jansen, Sebastian Junges, Ahmadreza Marandi, Marnix Suilen, Ufuk Topcu11792-11800
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the applicability of our algorithm using large instances of an aircraft collision-avoidance scenario and a novel spacecraft motion planning case study. and Numerical experiments. We demonstrate the applicability of the approach using two case studies. and We evaluate the new SCP-based approach to solve the u POMDP problem on two case studies. |
| Researcher Affiliation | Academia | 1Department of Aerospace Engineering and Engineering Mechanics, University of Texas at Austin, USA 2Department of Software Science, Radboud University, The Netherlands 3Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA 4Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, The Netherlands |
| Pseudocode | Yes | Algorithm 1 Sequential convex programming with trust region for solving uncertain POMDPs |
| Open Source Code | No | The paper does not state that its own implementation code is open source or provide a link to a code repository for the methodology described. |
| Open Datasets | No | The paper describes case studies and models derived from existing literature (e.g., Kochenderfer 2015, Kim et al. 2007) but does not refer to or provide access information for a specific publicly available dataset used for training/evaluation. |
| Dataset Splits | No | The paper does not specify exact dataset split percentages (e.g., train/validation/test splits) or provide sample counts for each split. |
| Hardware Specification | Yes | The experiments were performed on an Intel Core i9-9900u 2.50 GHz CPU and 64 GB of RAM |
| Software Dependencies | Yes | We use the verification tool Storm 1.6.2 (Dehnert et al. 2017) to build u POMDPs. The experiments were performed on an Intel Core i9-9900u 2.50 GHz CPU and 64 GB of RAM with Gurobi (Gurobi Optimization 2020) 9.0 as the LP solver and Storm s robust verification algorithm. |
| Experiment Setup | Yes | The algorithm parameters are τ = 104, δ = 1.5, γ = 1.5, and ω = 10 4. |